Zinc
/
sync
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: Zinc:2e773218be00463a27ad813d07c574f306e684d6
Branches Tags
Zinc:master
..
compare: Zinc:f6049fc64467acd6102594fda5358a2b016b5e1a
Branches Tags
Zinc:master

No commits in common. "2e773218be00463a27ad813d07c574f306e684d6" and "f6049fc64467acd6102594fda5358a2b016b5e1a" have entirely different histories.
2e773218be ... f6049fc644

4 changed files with 18 additions and 163 deletions
Show Stats Expand all files Collapse all files

4
include/sync/lexer.h
View File

@ -12,10 +12,6 @@ typedef enum {
TOKEN_LPAREN, TOKEN_LPAREN,
TOKEN_RPAREN, TOKEN_RPAREN,
TOKEN_SEMICOLON, TOKEN_SEMICOLON,
TOKEN_LBRACE,
TOKEN_RBRACE,
TOKEN_LBRACKET,
TOKEN_RBRACKET,
} TokenType; } TokenType;
typedef struct { typedef struct {

100
src/lexer.c
View File

@ -39,23 +39,6 @@ static char advance(Lexer *lexer) {
return lexer->source[lexer->pos++]; return lexer->source[lexer->pos++];
} }
typedef enum {
DIGIT_IS_BINARY = 1 << 0,
DIGIT_IS_OCTAL = 1 << 1,
DIGIT_IS_HEXADECIMAL = 1 << 2,
} DigitFlags;
static char is_digit_start(char c) {
return isdigit(c);
}
static char is_digit_char(char c, DigitFlags flags) {
if (flags & DIGIT_IS_BINARY) return c == '0' || c == '1' || c == '_';
if (flags & DIGIT_IS_OCTAL) return isdigit(c) && c < '8' || c == '_';
if (flags & DIGIT_IS_HEXADECIMAL) return isxdigit(c) || c == '_';
return isdigit(c) || c == '_';
}
static char is_identifier_start(char c) { static char is_identifier_start(char c) {
return isalpha(c) || c == '_'; return isalpha(c) || c == '_';
} }
@ -64,14 +47,6 @@ static char is_identifier_char(char c) {
return isalnum(c) || c == '_'; return isalnum(c) || c == '_';
} }
static TokenResult lexer_result(Lexer *lexer, TokenType type, size_t start, size_t start_line) {
return (TokenResult){SYNC_RESULT, .result = (Token){type, &lexer->source[start], lexer->pos - start, get_file_info(lexer, start, start_line)}};
}
static TokenResult lexer_error(Lexer *lexer, const char *message, size_t start, size_t start_line) {
return (TokenResult){SYNC_ERROR, .error = (SyncError){SYNC_LEXER_ERROR, message, get_file_info(lexer, start, start_line)}};
}
TokenResult lexer_next(Lexer *lexer) { TokenResult lexer_next(Lexer *lexer) {
// Gets the next token from the source // Gets the next token from the source
@ -89,79 +64,34 @@ TokenResult lexer_next(Lexer *lexer) {
// End of file tokens // End of file tokens
if (c == '\0') { if (c == '\0') {
return lexer_result(lexer, TOKEN_EOF, start, start_line); return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_EOF, &lexer->source[start], 0, get_file_info(lexer, start, start_line)}};
}
// Digits
if (isdigit(c)) {
DigitFlags flags = 0;
if (c == '0') {
advance(lexer);
if (peek(lexer) == 'b' || peek(lexer) == 'B') {
flags |= DIGIT_IS_BINARY; advance(lexer);
} else if (peek(lexer) == 'o' || peek(lexer) == 'O') {
flags |= DIGIT_IS_OCTAL; advance(lexer);
} else if (peek(lexer) == 'x' || peek(lexer) == 'X') {
flags |= DIGIT_IS_HEXADECIMAL; advance(lexer);
} else if (is_digit_char(peek(lexer), flags)) {
return lexer_error(lexer, "Invalid number format", start, start_line);
}
}
while (is_digit_char(peek(lexer), flags)) advance(lexer);
if (isspace(peek(lexer)) || peek(lexer) == ';' || peek(lexer) == '\0' || peek(lexer) == ')' || peek(lexer) == '(' || peek(lexer) == ',') {
return lexer_result(lexer, TOKEN_NUMBER, start, start_line);
} else {
return lexer_error(lexer, "Invalid number format", start, start_line);
}
} }
// Identifiers // Identifiers
if (is_identifier_start(c)) { if (is_identifier_start(c)) {
while (is_identifier_char(peek(lexer))) advance(lexer); while (is_identifier_char(peek(lexer))) advance(lexer);
return lexer_result(lexer, TOKEN_IDENTIFIER, start, start_line); return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_IDENTIFIER, &lexer->source[start], lexer->pos - start, get_file_info(lexer, start, start_line)}};
}
// Digits
if (isdigit(c)) {
while (isdigit(peek(lexer))) advance(lexer);
return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_NUMBER, &lexer->source[start], lexer->pos - start, get_file_info(lexer, start, start_line)}};
} }
advance(lexer); advance(lexer);
switch (c) { switch (c) {
case '=': case '=':
if (peek(lexer) == '=') advance(lexer); if (peek(lexer) == '=') return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_OPERATOR, &lexer->source[start], 2, get_file_info(lexer, start, start_line)}};
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '>':
if (peek(lexer) == '=' || peek(lexer) == '>') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '<':
if (peek(lexer) == '=' || peek(lexer) == '<') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '!':
if (peek(lexer) == '=') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '&':
if (peek(lexer) == '=' || peek(lexer) == '&') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '|':
if (peek(lexer) == '=' || peek(lexer) == '|') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '+': case '+':
if (peek(lexer) == '=') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '-': case '-':
if (peek(lexer) == '=') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '*': case '*':
if (peek(lexer) == '=') advance(lexer);
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line);
case '/': case '/':
if (peek(lexer) == '=') advance(lexer); return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_OPERATOR, &lexer->source[start], 1, get_file_info(lexer, start, start_line)}};
return lexer_result(lexer, TOKEN_OPERATOR, start, start_line); case '(': return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_LPAREN, &lexer->source[start], 1, get_file_info(lexer, start, start_line)}};
case '.': return lexer_result(lexer, TOKEN_OPERATOR, start, start_line); case ')': return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_RPAREN, &lexer->source[start], 1, get_file_info(lexer, start, start_line)}};
case ',': return lexer_result(lexer, TOKEN_OPERATOR, start, start_line); case ';': return (TokenResult){SYNC_RESULT, .result = (Token){TOKEN_SEMICOLON, &lexer->source[start], 1, get_file_info(lexer, start, start_line)}};
case '(': return lexer_result(lexer, TOKEN_LPAREN, start, start_line); default:
case ')': return lexer_result(lexer, TOKEN_RPAREN, start, start_line); return (TokenResult){SYNC_ERROR, .error = (SyncError){SYNC_LEXER_ERROR, "Unknown token", get_file_info(lexer, start, start_line)}};
case ';': return lexer_result(lexer, TOKEN_SEMICOLON, start, start_line);
case '}': return lexer_result(lexer, TOKEN_RBRACE, start, start_line);
case '{': return lexer_result(lexer, TOKEN_LBRACE, start, start_line);
case ']': return lexer_result(lexer, TOKEN_RBRACKET, start, start_line);
case '[': return lexer_result(lexer, TOKEN_LBRACKET, start, start_line);
default: return lexer_error(lexer, "Unknown token", start, start_line);
} }
} }

28
src/main.c
View File

@ -1,5 +1,4 @@
#include <stdio.h> #include <stdio.h>
#include <stdlib.h>
#include "sync/types.h" #include "sync/types.h"
#include "sync/lexer.h" #include "sync/lexer.h"
@ -7,35 +6,17 @@ static void print_token(Token token) {
printf("Token: %-15s | Text: '%.*s'\n", printf("Token: %-15s | Text: '%.*s'\n",
(const char *[]){ (const char *[]){
"EOF", "IDENTIFIER", "NUMBER", "OPERATOR", "EOF", "IDENTIFIER", "NUMBER", "OPERATOR",
"LPAREN", "RPAREN", "SEMICOLON", "LBRACE", "LPAREN", "RPAREN", "SEMICOLON", "UNKNOWN"
"RBRACE", "LBRACKET", "RBRACKET"
}[token.type], }[token.type],
(int)token.length, token.start (int)token.length, token.start
); );
} }
int main(void) { int main(void) {
const char *filename = "test/example1.zn"; const char *source = "sum = a + b123;\nprint(sum);";
FILE *file = fopen(filename, "rb");
if (!file) {
fprintf(stderr, "Failed to open file: %s\n", filename);
return 1;
}
fseek(file, 0, SEEK_END);
long filesize = ftell(file);
fseek(file, 0, SEEK_SET);
char *source = malloc(filesize + 1);
if (!source) {
fprintf(stderr, "Failed to allocate memory.\n");
fclose(file);
return 1;
}
fread(source, 1, filesize, file);
source[filesize] = '\0';
fclose(file);
Lexer lexer; Lexer lexer;
lexer_init(&lexer, filename, source); lexer_init(&lexer, "<stdin>", source);
TokenResult result; TokenResult result;
do { do {
@ -44,11 +25,8 @@ int main(void) {
print_token(result.result); print_token(result.result);
} else { } else {
fprintf(stderr, "Error: %s\n", result.error.message); fprintf(stderr, "Error: %s\n", result.error.message);
fprintf(stderr, "\tFilename: %s\n", result.error.file_info.filename);
fprintf(stderr, "\tLine: %zi\n", result.error.file_info.line);
} }
} while (result.type != SYNC_ERROR && result.result.type != TOKEN_EOF); } while (result.type != SYNC_ERROR && result.result.type != TOKEN_EOF);
free(source);
return 0; return 0;
} }

49
test/example1.zn
View File

@ -1,49 +0,0 @@
// Lexer Test Example1
// Currently not valid ZINC code
static void print_token(Token token) {
printf("Token: %-15s | Text: '%.*s'\n",
(const char *[]){
"EOF", "IDENTIFIER", "NUMBER", "OPERATOR",
"LPAREN", "RPAREN", "SEMICOLON", "UNKNOWN"
}[token.type],
(int)token.length, token.start
);
}
int main(void) {
const char *filename = "test/example1.zn";
FILE *file = fopen(filename, "rb");
if (!file) {
fprintf(stderr, "Failed to open file: %s\n", filename);
return 1;
}
fseek(file, 0, SEEK_END);
long filesize = ftell(file);
fseek(file, 0, SEEK_SET);
char *source = malloc(filesize + 1);
if (!source) {
fprintf(stderr, "Failed to allocate memory.\n");
fclose(file);
return 1;
}
fread(source, 1, filesize, file);
source[filesize] = '\0';
fclose(file);
Lexer lexer;
lexer_init(&lexer, filename, source);
TokenResult result;
do {
result = lexer_next(&lexer);
if (result.type == SYNC_RESULT) {
print_token(result.result);
} else {
fprintf(stderr, "Error: %s\n", result.error.message);
}
} while (result.type != SYNC_ERROR && result.result.type != TOKEN_EOF);
free(source);
return 0;
}